CN115660226B - Power load prediction model construction method and digital twin-based construction device - Google Patents
Power load prediction model construction method and digital twin-based construction device Download PDFInfo
- Publication number
- CN115660226B CN115660226B CN202211593076.0A CN202211593076A CN115660226B CN 115660226 B CN115660226 B CN 115660226B CN 202211593076 A CN202211593076 A CN 202211593076A CN 115660226 B CN115660226 B CN 115660226B
- Authority
- CN
- China
- Prior art keywords
- model
- historical
- coupling
- value
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010276 construction Methods 0.000 title abstract description 12
- 230000008878 coupling Effects 0.000 claims abstract description 121
- 238000010168 coupling process Methods 0.000 claims abstract description 121
- 238000005859 coupling reaction Methods 0.000 claims abstract description 121
- 238000003062 neural network model Methods 0.000 claims abstract description 73
- 238000000034 method Methods 0.000 claims abstract description 53
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 14
- 238000011161 development Methods 0.000 claims description 37
- 238000010606 normalization Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 13
- 238000012417 linear regression Methods 0.000 claims description 10
- 238000005065 mining Methods 0.000 claims description 5
- 238000004880 explosion Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 47
- 230000015654 memory Effects 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 241000272168 Laridae Species 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 230000003213 activating effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
Provided herein are a predictive model construction method of an electrical load and a digital twin-based construction apparatus, wherein the method comprises: acquiring historical influence factors of a target area; normalizing the history influencing factors; substituting the processed history influence factors into a preset coupling model to obtain coupling data; inputting the coupling data into a neural network model to obtain a predicted value of the neural network model; establishing an objective function and constraint conditions of the objective function according to the predicted value and the corresponding actual value of the power load; optimizing the objective function through an optimization algorithm to obtain an optimal solution of the objective function; respectively taking the weight and the bias corresponding to the optimal solution as the optimal weight and the optimal bias of the neural network model; and determining the optimized neural network model as a prediction model of the power load according to the optimal weight and the optimal bias. The prediction model obtained through construction can predict the future power load condition of the power system.
Description
Technical Field
The invention relates to the field of power systems, in particular to a method for constructing a prediction model of a power load and a device for constructing a power load based on digital twin.
Background
In the prior art, the current running state of the power system can only be visually monitored, and the prediction of the power load can not be performed, so that the subsequent development trend can not be timely and accurately deduced according to the current state of the power system, and the overload situation can be early warned in advance, so that great difficulty is brought to the running management and power dispatching control decision of the power system.
Therefore, a method for constructing a prediction model of a power load is needed, and future power load conditions of a power system can be predicted through the prediction model, so that early warning is performed on the condition that overload is likely to happen to the power system later.
Disclosure of Invention
An objective of embodiments herein is to provide a method for constructing a prediction model of a power load and a device for constructing a prediction model based on digital twinning, so as to predict a future power load condition of a power system through the prediction model, and further early warn a situation that overload may occur in a subsequent power system.
To achieve the above object, in one aspect, an embodiment herein provides a method for constructing a prediction model of an electrical load, including:
Acquiring historical influence factors of a target area;
normalizing the history influence factors;
substituting the normalized historical influence factors into a preset coupling model to obtain coupling data, wherein the coupling model is a model corresponding to the historical influence factors of the target area;
inputting the coupling data into a neural network model to obtain a predicted value output by the neural network model;
establishing an objective function and a constraint condition of the objective function according to the predicted value and the corresponding actual value of the power load;
optimizing the objective function through an optimization algorithm to obtain an optimal solution of the objective function;
respectively taking the weight and the bias corresponding to the optimal solution as the optimal weight and the optimal bias of the neural network model;
and determining the optimized neural network model as a prediction model of the power load according to the optimal weight and the optimal bias.
Preferably, the history influencing factors include: historical power load, historical meteorological data, historical electrical data, historical event conditions, and regional development index.
Preferably, the method for determining the preset coupling model includes:
establishing a thermal index coupling model according to historical meteorological data;
Establishing a meteorological coupling model according to historical meteorological data and the thermal index coupling model;
establishing an electric coupling model according to historical electric data and regional development indexes;
and establishing an event coupling model according to the historical event conditions.
Preferably, the establishing the thermal index coupling model according to the historical meteorological data further comprises:
the thermal index coupling model is expressed by the following formula:
wherein ,is a thermal index; t is the environment temperature after normalization treatment; r is the relative humidity after normalization treatment;are both thermal index coefficients.
Preferably, the establishing a weather coupling model according to the historical weather data and the thermal index coupling model further comprises:
the weather coupling model is expressed by the following formula:
wherein ,for weather coupling value, ++>For the thermal index, S is the normalized wind speed, < >>Is the corresponding coefficient when the thermal index is non-negative, ">Is the corresponding coefficient when the thermal index is negative, ">For the corresponding coefficient of wind speed, < > is->Is an interference value.
Preferably, the establishing the electric coupling model according to the historical electric data and the regional development index further comprises:
the electrical coupling model is expressed by the following formula:
Wherein D (x) is an electrical coupling value, D is a regional development index after normalization, I is a current value after normalization, E is a power value after normalization, f is a frequency value after normalization,for the coefficients corresponding to the regional development index, +.>For the coefficient corresponding to the current value, +.>For the coefficient corresponding to the power value, < >>Corresponding to frequency valueA number.
Preferably, the building the event coupling model according to the historical event situation further includes:
the event coupling model is expressed by the following formula:
wherein s (x) event coupling values.
Preferably, the inputting the coupling data into the neural network model, and obtaining the predicted value output by the neural network model further includes:
inputting the coupling data into a first neural network model to obtain a first output value;
inputting the first output value into a second neural network model to obtain a second output value so as to eliminate gradient explosion;
and inputting the second output value into a linear regression layer to obtain a predicted value.
Preferably, the establishing an objective function according to the predicted value and the corresponding actual value and the constraint condition of the objective function further includes:
The objective function and the constraint condition of the objective function are expressed by the following formulas:
wherein f (y) is an objective function,for the predicted value at time i +.>For the actual value at the i-th moment, n is the number of moments in time, s.t. is a constraint, m is a natural number greater than 0.5 and less than 1,/A>For weights in the first neural network model, +.>B is the bias in the first neural network model, which is the weight in the second neural network model,/->Is the bias of the linear regression layer.
In another aspect, embodiments herein provide a digital twinning-based power load prediction model building apparatus, the apparatus comprising:
the mining module is used for acquiring historical influence factors of the target area;
the cloud control analysis module is used for carrying out normalization processing on the history influence factors; substituting the normalized historical influence factors into a preset coupling model to obtain coupling data, wherein the coupling model is a model corresponding to the historical influence factors of the target area;
the virtual load prediction module is used for inputting the coupling data into the neural network model to obtain a predicted value output by the neural network model;
the load period deduction module is used for establishing an objective function and constraint conditions of the objective function according to the predicted value and the corresponding actual value of the power load; optimizing the objective function through an optimization algorithm to obtain an optimal solution of the objective function; respectively taking the weight and the bias corresponding to the optimal solution as the optimal weight and the optimal bias of the neural network model; and determining the optimized neural network model as a prediction model of the power load according to the optimal weight and the optimal bias.
According to the technical scheme provided by the embodiment of the invention, by the method of the embodiment of the invention, the history influence factors of the target area are comprehensively considered, all the history influence factors are coupled through the coupling model, the predicted value is obtained by inputting the coupling data into the neural network model, the objective function is further optimized through the difference between the predicted value and the actual value, and finally the optimized neural network model is obtained. According to the embodiment, all historical influence factors which possibly influence the power load are comprehensively considered, the influence factors are coupled in consideration of the influence factors and the relevance among the influence factors, the neural network model obtained through optimization is higher in accuracy, the actual situation of a target area is fitted, the future power load condition of the power system can be predicted, and further early warning is carried out on the situation that overload possibly occurs in the follow-up power system.
The foregoing and other objects, features and advantages will be apparent from the following more particular description of preferred embodiments, as illustrated in the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments herein or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments herein and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 illustrates a flow diagram of a method for predictive model construction of electrical loads provided by embodiments herein;
FIG. 2 is a flow chart illustrating a method for determining a preset coupling model provided by embodiments herein;
FIG. 3 is a schematic flow chart of inputting coupling data into a neural network model to obtain predicted values output by the neural network model according to the embodiments herein;
FIG. 4 is a schematic block diagram of a digital twin-based power load prediction model building apparatus according to an embodiment of the present disclosure;
fig. 5 shows a schematic structural diagram of a computer device provided in an embodiment herein.
Description of the drawings:
100. a mining module is used;
200. the cloud control analysis module;
300. a virtual load prediction module;
400. a load period deduction module;
502. a computer device;
504. a processor;
506. a memory;
508. a driving mechanism;
510. an input/output module;
512. an input device;
514. an output device;
516. a presentation device;
518. a graphical user interface;
520. a network interface;
522. a communication link;
524. a communication bus.
Detailed Description
The following description of the embodiments of the present disclosure will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the disclosure. All other embodiments, based on the embodiments herein, which a person of ordinary skill in the art would obtain without undue burden, are within the scope of protection herein.
In the prior art, the current running state of the power system can only be visually monitored, and the prediction of the power load can not be performed, so that the subsequent development trend can not be timely and accurately deduced according to the current state of the power system, and the overload situation can be early warned in advance, so that great difficulty is brought to the running management and power dispatching control decision of the power system.
To solve the above problems, embodiments herein provide a prediction model construction method of an electric load. FIG. 1 is a flow chart of a method of constructing a predictive model of an electrical load provided by embodiments herein, the present disclosure provides the method operational steps as described in the examples or flow charts, but may include more or fewer operational steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When a system or apparatus product in practice is executed, it may be executed sequentially or in parallel according to the method shown in the embodiments or the drawings.
It should be noted that the terms "first," "second," and the like in the description and claims herein and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or device.
Referring to fig. 1, provided herein is a predictive model construction method of an electrical load, comprising:
s101: acquiring historical influence factors of a target area;
s102: normalizing the history influence factors;
s103: substituting the normalized historical influence factors into a preset coupling model to obtain coupling data, wherein the coupling model is a model corresponding to the historical influence factors of the target area;
s104: inputting the coupling data into a neural network model to obtain a predicted value output by the neural network model;
s105: establishing an objective function and a constraint condition of the objective function according to the predicted value and the corresponding actual value of the power load;
s106: optimizing the objective function through an optimization algorithm to obtain an optimal solution of the objective function;
s107: respectively taking the weight and the bias corresponding to the optimal solution as the optimal weight and the optimal bias of the neural network model;
s108: and determining the optimized neural network model as a prediction model of the power load according to the optimal weight and the optimal bias.
The historical influence factors can be influence factors of the past year, influence factors of the past month and the like, and can comprise: historical power load, historical meteorological data, historical electrical data, historical event conditions, and regional development index. Specifically, the power load refers to the total power consumed by all electric equipment in the target area; meteorological data refers to ambient temperature, relative humidity, and wind speed within a target region; the electrical data refers to the total current, total power and total frequency of all electrical devices in the target area; historical event conditions refer to whether an event occurs in a target area, and generally, smooth holding of the event requires a guarantee of a power system, so that if an event occurs in the target area, additional attention is required to provide long-term effective power guarantee; the regional development index refers to the degree of development of a target region, and the more developed the target region, the higher the demand on the power system, and thus, for regions with higher degree of development, more stable power guarantee needs to be provided.
Further, the regional development index reflects the development degree of the target region, for example, the regional development index of the target region may be determined according to the annual GDP ranking, and the regional development index of the target region may be determined according to the ranking of the target region in the national GDP ranking of the province/municipality, for example, the national GDP ranking is divided into 3 levels from high to low, the regional development index is 3 if the regional development index is located at level 1, the regional development index is 2 if the regional development index is located at level 2, and the regional development index is 1 if the regional development index is located at level 3.
In acquiring the history influencing factors, taking one day as a unit and taking the history power load of the past 10 months as an example, the total power consumed by all electric equipment in the target area every day in the 31 days of 10 months needs to be acquired. Because the magnitude of the acquired history influence factors is larger, the history influence factors can be normalized so as to facilitate subsequent calculation. The historical power load, the historical meteorological data, the historical electrical data, the historical event situation and the regional development index can be normalized respectively during the normalization processing.
The preset coupling model comprises a thermal index coupling model, a meteorological coupling model, an electric coupling model and an event coupling model, wherein the coupling models are models corresponding to historical influence factors, and are composed of a plurality of different data, so that the different data are required to be coupled into one coupling data through the coupling model, and the coupling model can be used for coupling two data such as the historical electric data and the regional development index into one coupling data, so that the prediction of a subsequent neural network model is convenient.
Specifically, referring to fig. 2, the method for determining the preset coupling model includes:
s201: establishing a thermal index coupling model according to historical meteorological data;
s202: establishing a meteorological coupling model according to historical meteorological data and the thermal index coupling model;
s203: establishing an electric coupling model according to historical electric data and regional development indexes;
s204: and establishing an event coupling model according to the historical event conditions.
It should be noted that, since the historical power load itself is one data, there is no need to perform coupling, and when the neural network model is input, the historical power load is also required to be input into the neural network model, that is, the data input into the neural network model includes the respective coupling data obtained by the respective coupling models and the historical power load.
The neural network model may output a predicted value, which is a predicted power load, according to the input data, and may evaluate a prediction effect through an objective function after establishing the objective function according to the predicted value and an actual value of the power load.
In order to realize better predicted power load, the objective function can be optimized through an optimization algorithm, and the weight and bias corresponding to the optimal solution obtained through optimization are used as the optimal weight and the optimal bias of the neural network model, that is, the predicted value obtained through prediction of the neural network model after the optimal weight and the optimal bias are set is closest to the actual value, so that the optimized neural network model can be obtained.
According to the method, historical influence factors of a target area are comprehensively considered, all the historical influence factors are coupled through a coupling model, a predicted value is obtained by inputting coupling data into a neural network model, an objective function is further optimized through the difference between the predicted value and an actual value, and finally the optimized neural network model is obtained. According to the embodiment, all historical influence factors which possibly influence the power load are comprehensively considered, the influence factors are coupled in consideration of the influence factors and the relevance among the influence factors, the neural network model obtained through optimization is higher in accuracy, the actual situation of a target area is fitted, the future power load condition of the power system can be predicted, and further early warning is carried out on the situation that overload possibly occurs in the follow-up power system.
In the embodiment herein, the history influencing factors may be normalized by the following formula:
wherein ,is the history influence factor after normalization processing, x is the history influence factor before normalization processing,is the minimum value of history influence factors before normalization processing,/ >Is the maximum value of the history influence factors before normalization processing.
Since the history influence factors include the history power load, the history weather data, the history electric data, the history event situation and the regional development index, the process of the normalization processing is described by taking the history power load therein as an example, since the history power load of 31 days is obtained in one unit of one day when the history influence factors are obtained, the above formula is used when the history power load of one day is normalized, whereinIs a power load value corresponding to the day where the historical power load is smallest among 31 days, wherein +.>The power load value corresponding to the day with the largest historical power load in 31 days is obtained through calculation, and then the historical influence factor after normalization processing of a certain day is obtained. />
In embodiments herein, the establishing a thermal index coupling model from historical meteorological data further comprises:
the thermal index coupling model is expressed by the following formula:
wherein ,is a thermal index; t is the environment temperature after normalization treatment; r is the relative humidity after normalization treatment;are both thermal index coefficients.
the environment temperature and the relative humidity are two values which can influence each other, so that the environment temperature and the relative humidity are coupled through a thermal index coupling model to obtain coupling data after the two values are coupled, and the coupling data can influence the prediction of the power load. The thermal index coefficient is obtained through historical data fitting, and is applied to a thermal index coupling model, so that the relation between load and climate can be reflected better.
In embodiments herein, the establishing a weather coupling model from the historical weather data and the thermal index coupling model further comprises:
the weather coupling model is expressed by the following formula:
wherein ,for weather coupling value, ++>For the thermal index, S is the normalized wind speed, < >>Is the corresponding coefficient when the thermal index is non-negative, ">Is the corresponding coefficient when the thermal index is negative, ">For the corresponding coefficient of wind speed, < > is->Is an interference value.
Wherein the coefficients are、/> and />And interference value ∈>The specific value of (2) can be determined according to the actual working condition, and will not be described in detail herein.
The thermal index is obtained after the ambient temperature and the relative humidity are coupled, and the ambient temperature, the relative humidity and the wind speed are also three values which can influence each other, so that the ambient temperature, the relative humidity and the wind speed are coupled through a meteorological coupling model to obtain a meteorological coupling value after the three values are coupled, and the meteorological coupling value can influence the prediction of the power load. The climate factors are comprehensively considered, so that the relation between the load and the climate can be better reflected.
In embodiments herein, the establishing the electrical coupling model based on the historical electrical data and the regional development index further comprises:
The electrical coupling model is expressed by the following formula:
wherein D (x) is an electrical coupling value, D is a regional development index after normalization, I is a current value after normalization, E is a power value after normalization, f is a frequency value after normalization,for the coefficients corresponding to the regional development index, +.>For the coefficient corresponding to the current value, +.>For the coefficient corresponding to the power value, < >>Is the coefficient corresponding to the frequency value.
Wherein the coefficients are、/>、/> and />The specific value of (2) can be determined according to the actual working condition, and will not be described in detail herein.
Generally, the regional development index, the current value, the power value and the frequency value are four values which can affect each other, for example, the higher the regional development index is, the larger the total current value, the total power value and the total frequency value of the region are, so that the regional development index, the current value, the power value and the frequency value are coupled through an electric coupling model to obtain electric coupling values after the four values are coupled, and the electric coupling values can affect the prediction of the electric load. And the electrical factors are comprehensively considered, so that the relation between the load and the electrical data can be better reflected.
In an embodiment herein, the building the event coupling model based on the historical event conditions further includes:
The event coupling model is expressed by the following formula:
wherein s (x) event coupling values.
The presence or absence of an event affects the prediction of the power load for the event, but since the event itself is not continuous but has a sudden or occasional nature, the event can be considered alone to obtain an event coupling value.
In this embodiment, referring to fig. 3, the inputting the coupling data into the neural network model, obtaining the predicted value output by the neural network model further includes:
s301: inputting the coupling data into a first neural network model to obtain a first output value;
s302: inputting the first output value into a second neural network model to obtain a second output value so as to eliminate gradient explosion;
s303: and inputting the second output value into a linear regression layer to obtain a predicted value.
According to the above, the input of the first neural network model includes the historical power load in addition to the three coupling values, the three coupling values and the historical power load are combined into a four-dimensional vector, and the four-dimensional vector is input to the first neural network model to obtain the first output value.
The first neural network model can be an LSTM neural network model, and four-dimensional vectors are input and then sequentially pass through a forgetting gate, an input gate and an output gate.
The calculation formula related to the forgetting door is specifically as follows:
wherein ,is the input information at time t; />The state of the hidden layer at the time t-1; />Activating a function for sigmoid; />Weight for forget gate; />Bias for forgetting the door; />And the forgetting gate output at the time t is shown.
The input gate-related calculation formula is specifically:
wherein ,an output being an input gate; />Bias for the input gate; />Is the weight of the input gate.
The calculation formula of the output gate is specifically:
After passing through the forgetting gate, the input gate and the output gate in turn, the state of the hidden layer at the next moment needs to be updated, and the specific formula is as follows:
wherein ,updating the state value of the neuron at the previous t moment; />The state value of the neuron at the time t; />The state value of the neuron at the time t-1; />Representing the multiplication of the elements of the matrix; />Weights for neuronal states; />Bias for neuronal state; />The state of the hidden layer at the time t; tanh is the hyperbolic tangent activation function.
Wherein the second neural network model may be a GRU neural network model, to The input is passed through the update gate, reset gate and gate control switching unit once.
The calculation formula related to the updated gate is specifically:
The calculation formula related to the reset gate is specifically as follows:
The gate control channel switching unit is used for calculating an implicit state value at the time t, and the related calculation formula is specifically as follows:
wherein ,at time tImplicit state value of->Is an implicit state value at time t-1, < >>For candidate hidden states, the candidate hidden states are calculated by the following formula:
In order to realize regression prediction, a linear regression layer is added, a second output value is input into the linear regression layer, and a formula for obtaining a predicted value is as follows:
wherein ,、/>the weight and bias of the linear regression layer are respectively; y is a predicted value.
After obtaining the predicted value, establishing an objective function and a constraint condition of the objective function according to the predicted value and the corresponding actual value further comprises:
the objective function and the constraint condition of the objective function are expressed by the following formulas:
Wherein f (y) is an objective function,for the predicted value at time i +.>For the actual value at the i-th moment, n is the number of moments in time, s.t. is a constraint, m is a natural number greater than 0.5 and less than 1,/A>For weights in the first neural network model, +.>B is the bias in the first neural network model, which is the weight in the second neural network model,/->Is the bias of the linear regression layer.
wherein Is weight including->;/>Is weight including->The method comprises the steps of carrying out a first treatment on the surface of the b is bias includingWhen the values in the constraint conditions are different, the corresponding obtained predicted values are also different, the difference between the predicted values and the actual values is also different, and the solutions of the obtained objective functions are also different.
And when the objective function takes the optimal solution, the weights and the biases in the corresponding constraint conditions are the optimal weights and the optimal biases of the neural network model, so that the optimal neural network model is obtained, and the optimal neural network model comprises an optimal first neural network model and an optimal second neural network model.
The optimization algorithm may be a seagull optimization algorithm, and the specific steps of the seagull optimization algorithm are as follows:
Step 1: and calculating an optimal solution and an optimal seagull position of the objective function according to the objective function.
Step 2: additional variable A is introduced to update individual seagull positions so as to avoid collision with other seabirds:
wherein ,for the current individual position->Representing a new position having no position conflict with other seagulls; a represents the motion behavior of seagulls in a designated space; k is the current iteration number; />Setting the control factor to 2; m is the maximum number of iterations, < >>For the optimal relative direction of the individual->Representing the location of the optimal individual; wherein rd is [0,1]The inner one obeys a random number distributed uniformly.
Step 3: determining a relative distance to the optimal individual:
after the gull successfully judges the relative direction with the optimal individual, the relative distance is determined:
in the formula ,representing the relative distance between the seagull individual and the optimal individual;
step 4: in the attack, the sea gull individual continuously changes the angle and the speed to do spiral motion in the air, and the position updating formula when the sea gull individual executes the attack is as follows:
wherein u, v, w represent the motion behavior of individual seagull to attack hunting object in three-dimensional space, r represents the radius of each circle of spiral line, alpha represents the flying angle of the seagull when making spiral motion, h and k are constants defining the spiral shape, the base number of natural logarithm of e, and alpha is a random number in the range of 0,2 pi.
Step 5: performing iterative computation on the objective function based on constraint conditions and a seagull optimization algorithm; in each iteration process, the sea-gull optimization algorithm calculates solutions of all objective functions corresponding to different sea-gull individuals, and selects from solutions corresponding to all sea-gull individuals according to the solutions of the objective functions, and updates the sea-gull individual positions at the same time. Then, circulating, if the termination condition is met, outputting the current solution of the objective function as the optimal solution, and ending the program; the termination condition is typically taken when none of the new solutions in consecutive chains is accepted or the maximum number of iterations is reached; otherwise, returning to step 1, i.e. the accepted new solution is always generated, and the result is increasingly converged to an optimal solution, i.e. the minimum value of f (y), and the constraint condition values at this moment are the optimal weight and the optimal bias of the LSTM-GRU network.
Based on the power load prediction model construction method disclosed by the embodiment of the invention, a power load prediction method can be further provided, wherein the prediction method collects the influence factors of the current day, and inputs the influence factors of the current day into the model constructed by the prediction model construction method to obtain the power load prediction value of the open day.
Of course, after the actual value of the power load is obtained in open sun, the objective function can be optimized according to the predicted value and the actual value, and the optimal weight and the optimal bias of the neural network model are further obtained.
It should be noted that, the method for predicting the power load described in the embodiments herein may be implemented based on a prediction device, where the prediction device may be connected to a terminal interaction platform, and the terminal interaction platform is configured to visually display the collected influence factors of the day and the predicted power load predicted value of the tomorrow. The device can also be connected with a power system for controlling the power system according to the power load predicted value of the open day so as to provide more stable and effective power load.
It should be noted that, user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party. In addition, the technical scheme described in the embodiment of the application accords with the relevant regulations of national laws and regulations for data acquisition, storage, use, processing and the like.
Based on the above-mentioned method for constructing a prediction model of an electrical load, an embodiment herein further provides a device for constructing a prediction model of an electrical load. The described devices may include systems (including distributed systems), software (applications), modules, components, servers, clients, etc. that employ the methods described in embodiments herein in combination with the necessary devices to implement the hardware. Based on the same innovative concepts, the embodiments herein provide for devices in one or more embodiments as described in the following examples. Since the implementation of the device for solving the problem is similar to the method, the implementation of the device in the embodiment herein may refer to the implementation of the foregoing method, and the repetition is not repeated. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Specifically, fig. 4 is a schematic block diagram of an embodiment of a power load prediction model building apparatus based on digital twin provided in the embodiment herein, and referring to fig. 4, the power load prediction model building apparatus based on digital twin provided in the embodiment herein includes: the system comprises a mining module 100, a cloud control analysis module 200, a virtual load prediction module 300 and a load period deduction module 400.
The mining module 100 is used for acquiring historical influence factors of a target area;
the cloud control analysis module 200 is used for carrying out normalization processing on the history influence factors; substituting the normalized historical influence factors into a preset coupling model to obtain coupling data, wherein the coupling model is a model corresponding to the historical influence factors of the target area;
the virtual load prediction module 300 is configured to input the coupling data to a neural network model, so as to obtain a predicted value output by the neural network model;
the load period deduction module 400 is configured to establish an objective function and a constraint condition of the objective function according to the predicted value and the corresponding actual value of the power load; optimizing the objective function through an optimization algorithm to obtain an optimal solution of the objective function; respectively taking the weight and the bias corresponding to the optimal solution as the optimal weight and the optimal bias of the neural network model; and determining the optimized neural network model as a prediction model of the power load according to the optimal weight and the optimal bias.
Referring to fig. 5, a computer device 502 is further provided in an embodiment herein based on a method for constructing a prediction model of an electrical load as described above, where the method is run on the computer device 502. The computer device 502 may include one or more processors 504, such as one or more Central Processing Units (CPUs) or Graphics Processors (GPUs), each of which may implement one or more hardware threads. The computer device 502 may also comprise any memory 506 for storing any kind of information, such as code, settings, data, etc., and in a specific embodiment a computer program on the memory 506 and executable on the processor 504, which computer program, when being executed by said processor 504, may execute instructions according to the method described above. For example, and without limitation, memory 506 may include any one or more of the following combinations: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any memory may store information using any technique. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent fixed or removable components of computer device 502. In one case, when the processor 504 executes associated instructions stored in any memory or combination of memories, the computer device 502 can perform any of the operations of the associated instructions. The computer device 502 also includes one or more drive mechanisms 508, such as a hard disk drive mechanism, an optical disk drive mechanism, and the like, for interacting with any memory.
The computer device 502 may also include an input/output module 510 (I/O) for receiving various inputs (via an input device 512) and for providing various outputs (via an output device 514). One particular output mechanism may include a presentation device 516 and an associated graphical user interface 518 (GUI). In other embodiments, input/output module 510 (I/O), input device 512, and output device 514 may not be included, but merely as a computer device in a network. Computer device 502 may also include one or more network interfaces 520 for exchanging data with other devices via one or more communication links 522. One or more communication buses 524 couple the above-described components together.
Corresponding to the method in fig. 1-3, embodiments herein also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method.
Embodiments herein also provide a computer readable instruction wherein the program therein causes the processor to perform the method as shown in fig. 1 to 3 when the processor executes the instruction.
It should be understood that, in the various embodiments herein, the sequence number of each process described above does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments herein.
It should also be understood that in embodiments herein, the term "and/or" is merely one relationship that describes an associated object, meaning that three relationships may exist. For example, a and/or B may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided herein, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the elements may be selected according to actual needs to achieve the objectives of the embodiments herein.
In addition, each functional unit in the embodiments herein may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions herein are essentially or portions contributing to the prior art, or all or portions of the technical solutions may be embodied in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments herein. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Specific examples are set forth herein to illustrate the principles and embodiments herein and are merely illustrative of the methods herein and their core ideas; also, as will be apparent to those of ordinary skill in the art in light of the teachings herein, many variations are possible in the specific embodiments and in the scope of use, and nothing in this specification should be construed as a limitation on the invention.
Claims (8)
1. The method for constructing the prediction model of the power load is characterized by comprising the following steps of:
acquiring historical influence factors of a target area; the historical influencing factors comprise historical power loads, historical meteorological data, historical electrical data, historical event conditions and regional development indexes;
normalizing the history influence factors;
substituting the normalized historical influence factors into a preset coupling model to obtain coupling data, wherein the coupling model is a model corresponding to the historical influence factors of the target area;
inputting the coupling data into a first neural network model to obtain a first output value;
inputting the first output value into a second neural network model to obtain a second output value so as to eliminate gradient explosion;
Inputting the second output value to a linear regression layer to obtain a predicted value;
establishing an objective function and a constraint condition of the objective function according to the predicted value and the corresponding actual value of the power load;
optimizing the objective function through an optimization algorithm to obtain an optimal solution of the objective function;
respectively taking the weight and the bias corresponding to the optimal solution as the optimal weight and the optimal bias of the neural network model;
and determining the optimized neural network model as a prediction model of the power load according to the optimal weight and the optimal bias.
2. The method for constructing a predictive model of an electrical load according to claim 1, wherein the method for determining the predetermined coupling model comprises:
establishing a thermal index coupling model according to historical meteorological data;
establishing a meteorological coupling model according to historical meteorological data and the thermal index coupling model;
establishing an electric coupling model according to historical electric data and regional development indexes;
and establishing an event coupling model according to the historical event conditions.
3. The method of claim 2, wherein the establishing a thermal index coupling model from historical meteorological data further comprises:
The thermal index coupling model is expressed by the following formula:
4. The method of claim 2, wherein the establishing a weather coupling model from the historical weather data and the thermal index coupling model further comprises:
the weather coupling model is expressed by the following formula:
wherein ,for weather coupling value, ++>For the thermal index, S is the normalized wind speed, < >>Is the corresponding coefficient when the thermal index is non-negative, ">Is the corresponding coefficient when the thermal index is negative, ">For the corresponding coefficient of wind speed, < > is->Is an interference value.
5. The method of claim 2, wherein the establishing an electrical coupling model from the historical electrical data and the regional development index further comprises:
the electrical coupling model is expressed by the following formula:
wherein D (x) is an electrical coupling value, D is a regional development index after normalization, I is a current value after normalization, E is a power value after normalization, f is a frequency value after normalization, For the coefficients corresponding to the regional development index, +.>For the coefficient corresponding to the current value, +.>For the coefficient corresponding to the power value, < >>Is the coefficient corresponding to the frequency value.
7. The method according to claim 1, wherein the establishing an objective function from the predicted value and the corresponding actual value and a constraint condition of the objective function further comprises:
the objective function and the constraint condition of the objective function are expressed by the following formulas:
wherein f (y) is an objective function,for the predicted value at time i +.>For the actual value at the i-th moment, n is the number of moments in time, s.t. is a constraint, m is a natural number greater than 0.5 and less than 1,/A>For weights in the first neural network model, +.>B is the bias in the first neural network model, which is the weight in the second neural network model,/->Is the bias of the linear regression layer.
8. A digital twinning-based power load prediction model building apparatus, the apparatus comprising:
the mining module is used for acquiring historical influence factors of the target area; the historical influencing factors comprise historical power loads, historical meteorological data, historical electrical data, historical event conditions and regional development indexes;
the cloud control analysis module is used for carrying out normalization processing on the history influence factors; substituting the normalized historical influence factors into a preset coupling model to obtain coupling data, wherein the coupling model is a model corresponding to the historical influence factors of the target area;
the virtual load prediction module is used for inputting the coupling data into a first neural network model to obtain a first output value; inputting the first output value into a second neural network model to obtain a second output value so as to eliminate gradient explosion; inputting the second output value to a linear regression layer to obtain a predicted value;
the load period deduction module is used for establishing an objective function and constraint conditions of the objective function according to the predicted value and the corresponding actual value of the power load; optimizing the objective function through an optimization algorithm to obtain an optimal solution of the objective function; respectively taking the weight and the bias corresponding to the optimal solution as the optimal weight and the optimal bias of the neural network model; and determining the optimized neural network model as a prediction model of the power load according to the optimal weight and the optimal bias.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211593076.0A CN115660226B (en) | 2022-12-13 | 2022-12-13 | Power load prediction model construction method and digital twin-based construction device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211593076.0A CN115660226B (en) | 2022-12-13 | 2022-12-13 | Power load prediction model construction method and digital twin-based construction device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115660226A CN115660226A (en) | 2023-01-31 |
CN115660226B true CN115660226B (en) | 2023-04-25 |
Family
ID=85017277
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211593076.0A Active CN115660226B (en) | 2022-12-13 | 2022-12-13 | Power load prediction model construction method and digital twin-based construction device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115660226B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116702978B (en) * | 2023-06-07 | 2024-02-13 | 西安理工大学 | Electric vehicle charging load prediction method and device considering emergency characteristics |
CN116956594B (en) * | 2023-07-25 | 2024-02-09 | 广州锐兴科技有限公司 | Rural power grid optimization method, device and equipment based on topological structure |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115293400A (en) * | 2022-06-23 | 2022-11-04 | 国网浙江省电力有限公司营销服务中心 | Power system load prediction method and system |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111275240B (en) * | 2019-12-27 | 2023-06-09 | 华北电力大学 | Load prediction method based on multi-energy coupling scene |
CN112116153B (en) * | 2020-09-18 | 2022-10-04 | 上海电力大学 | Park multivariate load joint prediction method coupling Copula and stacked LSTM network |
AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
CN113610328A (en) * | 2021-08-25 | 2021-11-05 | 浙江浙能台州第二发电有限责任公司 | Power generation load prediction method |
CN113762387B (en) * | 2021-09-08 | 2024-02-02 | 东北大学 | Multi-element load prediction method for data center station based on hybrid model prediction |
CN115293326A (en) * | 2022-07-05 | 2022-11-04 | 深圳市国电科技通信有限公司 | Training method and device of power load prediction model and power load prediction method |
CN115423161A (en) * | 2022-08-19 | 2022-12-02 | 国网山东省电力公司电力科学研究院 | Digital twin-based multi-energy coupling optimization scheduling method and system |
CN115276006B (en) * | 2022-09-26 | 2022-12-13 | 江苏永鼎股份有限公司 | Load prediction method and system for power integration system |
-
2022
- 2022-12-13 CN CN202211593076.0A patent/CN115660226B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115293400A (en) * | 2022-06-23 | 2022-11-04 | 国网浙江省电力有限公司营销服务中心 | Power system load prediction method and system |
Non-Patent Citations (1)
Title |
---|
Dongxiao Niu 等.Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism.《Applied Energy》.2022,第313卷第1-15 页. * |
Also Published As
Publication number | Publication date |
---|---|
CN115660226A (en) | 2023-01-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115660226B (en) | Power load prediction model construction method and digital twin-based construction device | |
US20210381712A1 (en) | Determining demand curves from comfort curves | |
Hota et al. | Time series data prediction using sliding window based RBF neural network | |
JP2022527536A (en) | Improving fairness through reinforcement learning | |
US11775721B2 (en) | Quantum circuit decomposition by integer programming | |
CN112862012A (en) | Operation and maintenance system abnormity early warning method, device and equipment based on LSTM model | |
US11663486B2 (en) | Intelligent learning system with noisy label data | |
CN109086930B (en) | User electricity consumption behavior analysis method based on power K line graph and deep network | |
CN110264270A (en) | A kind of behavior prediction method, apparatus, equipment and storage medium | |
CN113302605A (en) | Robust and data efficient black box optimization | |
US20210374544A1 (en) | Leveraging lagging gradients in machine-learning model training | |
CN111027672A (en) | Time sequence prediction method based on interactive multi-scale recurrent neural network | |
US11295236B2 (en) | Machine learning in heterogeneous processing systems | |
US20240028897A1 (en) | Interpreting convolutional sequence model by learning local and resolution-controllable prototypes | |
US20220092464A1 (en) | Accelerated machine learning | |
CN117076993A (en) | Multi-agent game decision-making system and method based on cloud protogenesis | |
CN114817571B (en) | Dynamic knowledge graph-based achievement quoted quantity prediction method, medium and equipment | |
CN112990958A (en) | Data processing method, data processing device, storage medium and computer equipment | |
CN115879369A (en) | Coal mill fault early warning method based on optimized LightGBM algorithm | |
Sanzana et al. | Charging water load prediction for a thermal-energy-storage air-conditioner of a commercial building with a multilayer perceptron | |
Alam | Recurrent neural networks in electricity load forecasting | |
CN112232557B (en) | Short-term prediction method for health degree of switch machine based on long-short-term memory network | |
Sarıkaya et al. | Training Sigma-Pi neural networks with the grey wolf optimization algorithm | |
Tak | A novel ARMA type possibilistic fuzzy forecasting functions based on grey-wolf optimizer (ARMA-PFFs) | |
CN113254857A (en) | SSA-ELM-based short-term power load prediction method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |